AI News

⚡ 1 minute ago
1
1
TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning (arxiv.org)
2
1
Libra: Efficient Resource Management for Agentic RL Post-Training (arxiv.org)
3
1
Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR (arxiv.org)
4
1
Social Caption: Evaluating Social Understanding in Multimodal Models (arxiv.org)
5
1
Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs (arxiv.org)
6
1
Evaluating Transformer and LSTM Frameworks for Prediction in Ungauged Basins (arxiv.org)
7
1
Generating Rectifiable Measures through Neural Networks (arxiv.org)
8
1
Human-in-the-Loop Contextual Bandits for Short-Term Rental Dynamic Pricing: Structural Equivalence of Historical Warm-Up and Approval-Gated Live Learning (arxiv.org)
9
1
StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems (arxiv.org)
10
1
Representational Capacity: Geometric Limits on Feature Representation in Transformer Language Models (arxiv.org)
11
1
Making Brain-Computer Interfaces More Secure (arxiv.org)
12
1
Scalable Uncertainty Quantification for Extreme Weather Forecasting via Empirical Neural Tangent Kernels (arxiv.org)
13
1
Visual Graph Scaffolds for Structural Reasoning in Large Language Models (arxiv.org)
14
1
$\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval (arxiv.org)
15
1
$\Psi$-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues (arxiv.org)
16
1
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning (arxiv.org)
17
1
Learn When and Where to Connect: Adaptive Virtual Nodes for Dynamic Message Passing on Graphs (arxiv.org)
18
1
Do Real-World Datasets Contain Natural Experiments? An Empirical Study Using Causal Feature Selection (arxiv.org)
19
1
Local and Global Contraction Principles for MCMC Mixing (arxiv.org)
20
1
Spectral Asymptotics of Neural Network Loss Landscapes: An Exact Decomposition of the Curvature Exponent (arxiv.org)
21
1
Hierarchies of Calibration: Classification meets Regression (arxiv.org)
22
1
The Value Function Semi-Algebraic Set in Partially Observable Markov Decision Processes (arxiv.org)
23
1
Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models (arxiv.org)
24
1
RRISE: Robust Radius Inference via a Surrogate Estimator (arxiv.org)
25
1
ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning (arxiv.org)
26
1
SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale (arxiv.org)
27
1
Impact of Graph Structure on Membership-Inference Risk for Graph Neural Networks (arxiv.org)
28
1
ParaBlock: Communication-Computation Parallel Block Coordinate Federated Learning for Large Language Models (arxiv.org)
29
1
A Single-Loop Bilevel Deep Learning Method for Optimal Control of Obstacle Problems (arxiv.org)
30
1
A Robust Optimization Approach to Sparse Principal Component Analysis (arxiv.org)
31
1
Trajectory-Aware Node Contributions and the Limits of Static Controllability (arxiv.org)
32
1
A formal definition and meta-model for a machine theory of mind (arxiv.org)
33
1
Rethinking Molecular Text Representations for LLMs: An Empirical Study (arxiv.org)
34
1
Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments (arxiv.org)
35
1
Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation (arxiv.org)
36
1
The DeepSpeak-Agentic Dataset (arxiv.org)
37
1
Dynamic Objective Selection with Safeguards and LLM Oversight for Financial Decision-Making (arxiv.org)
38
1
Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models (arxiv.org)
39
1
An Asymptotic Theory of Chain-of-Thought in In-Context Learning (arxiv.org)
40
1
Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs (arxiv.org)
41
1
A Cartesian-3j Framework for Machine Learning Interatomic Potentials (arxiv.org)
42
1
A Fast Screening Approach for High-dimensional Outcomes and High-dimensional Predictors (arxiv.org)
43
1
Towards Blind Lens Aberration Correction via Large LensLib Pre-training and Discrete Degradation Priors (arxiv.org)
44
1
Distill-then-Replace: Efficient Task-Specific Hybrid Attention Model Construction (arxiv.org)
45
1
Optimized Labeling Resource Allocation for Prediction-Assisted Inference via OPAL (arxiv.org)
46
1
Greed is Good: A Unifying Perspective on Guided Generation (arxiv.org)
47
1
Evaluating the Impact of COVID-19 Vaccination in the United Kingdom: A Gaussian Process Approach (arxiv.org)
48
1
A Factorized Low-Rank RNN Framework for Uncovering Independent Neural Latent Dynamics and Connectivity (arxiv.org)
49
1
SAIL: Sound Abstract Interpreters with LLMs (arxiv.org)
50
1
Can Local Learning Match Self-Supervised Backpropagation? (arxiv.org)